test_python.yml

on:
  push:
    branches-ignore:
      - "gh-readonly-queue/**"
      - "copilot/**"
      - "dependabot/**"
      - "pre-commit-ci-update-config"
  pull_request:
  merge_group:
concurrency:
  group: ${{ github.workflow }}-${{ github.ref || github.run_id }}
  cancel-in-progress: true
name: Test Python
jobs:
  testpython:
    name: Test Python
    runs-on: ubuntu-22.04
    strategy:
      fail-fast: false
      matrix:
        group: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
        # Pull requests only run the oldest supported Python version.
        # Push and merge queue runs keep the full version matrix.
        python: ${{ fromJSON(github.event_name == 'pull_request' && '["3.10"]' || '["3.10", "3.13"]') }}

    steps:
      - uses: actions/checkout@v7
      - uses: actions/setup-python@v7
        with:
          python-version: ${{ matrix.python }}
      - run: python -m pip install -U uv
      - run: |
          source/install/uv_with_retry.sh pip install --system openmpi --group pin_tensorflow_cpu --group pin_pytorch_cpu --torch-backend cpu
          export TENSORFLOW_ROOT=$(python -c 'import importlib.util,pathlib;print(pathlib.Path(importlib.util.find_spec("tensorflow").origin).parent)')
          export PYTORCH_ROOT=$(python -c 'import torch;print(torch.__path__[0])')
          source/install/uv_with_retry.sh pip install --system -e .[test,jax,torch] mpi4py --group pin_jax_cpu
          source/install/uv_with_retry.sh pip install --system --find-links "https://www.paddlepaddle.org.cn/packages/nightly/cpu/paddlepaddle/" --index-url https://pypi.org/simple --trusted-host www.paddlepaddle.org.cn --trusted-host paddlepaddle.org.cn paddlepaddle==3.4.0.dev20260310
        env:
          # Please note that uv has some issues with finding
          # existing TensorFlow package. Currently, it uses
          # TensorFlow in the build dependency, but if it
          # changes, setting `TENSORFLOW_ROOT`.
          DP_ENABLE_PYTORCH: 1
          DP_BUILD_TESTING: 1
          HOROVOD_WITH_TENSORFLOW: 1
          HOROVOD_WITHOUT_PYTORCH: 1
          HOROVOD_WITH_MPI: 1
          # https://cmake.org/cmake/help/latest/variable/CMAKE_POLICY_VERSION_MINIMUM.html
          CMAKE_POLICY_VERSION_MINIMUM: 3.5
          UV_HTTP_TIMEOUT: 120
      - run: dp --version
      - name: Get durations from cache
        uses: actions/cache@v6
        with:
          path: .test_durations
          # the key must never match, even when restarting workflows, as that
          # will cause durations to get out of sync between groups, the
          # combined durations will be loaded if available
          key: test4-durations-split-${{ github.run_id }}-${{ github.run_number }}-${{ github.run_attempt }}-${{ matrix.python }}-${{ matrix.group }}
          restore-keys: |
            test4-durations-combined-${{ matrix.python }}-${{ github.sha }}
            test4-durations-combined-${{ matrix.python }}
      - name: Prepare independent duration inputs
        run: |
          for output in main tf2 jax2tf consistent_tf2; do
            if [ -f .test_durations ]; then
              cp .test_durations ".test_durations_${output}"
            fi
          done
      # Keep fixture-sharing classes/modules together, then balance those
      # indivisible units by their recorded durations.
      - run: python -m pytest -p source.tests.ci_split --cov=deepmd source/tests --ignore=source/tests/tf2 --ci-splits 12 --ci-group ${{ matrix.group }} --store-durations --clean-durations --durations-path=.test_durations_main
        env:
          NUM_WORKERS: 0
          DP_CI_IMPORT_PADDLE_BEFORE_TF: 1
          FLAGS_use_stride_compute_kernel: 0
      - name: Test TF2 eager mode
        run: |
          run_pytest_allow_no_tests() {
            local durations_path=$1
            shift
            set +e
            pytest "$@" \
              --store-durations \
              --clean-durations \
              --durations-path="$durations_path"
            local status=$?
            set -e
            if [ "$status" -eq 5 ]; then
              # pytest-split may leave an individual shard with no selected
              # tests after path/-k filtering. Other shards still cover the
              # selected tests, so do not fail the whole matrix for exit 5.
              printf '{}\n' > "$durations_path"
              return 0
            fi
            return "$status"
          }

          run_pytest_allow_no_tests .test_durations_tf2 \
            --cov=deepmd --cov-append \
            source/tests/tf2 \
            --splits 12 \
            --group ${{ matrix.group }}
          run_pytest_allow_no_tests .test_durations_jax2tf \
            --cov=deepmd --cov-append \
            source/tests/consistent/io/test_io.py \
            source/jax2tf_tests \
            --splits 12 \
            --group ${{ matrix.group }}
          run_pytest_allow_no_tests .test_durations_consistent_tf2 \
            --cov=deepmd --cov-append \
            source/tests/consistent \
            -k tf2 \
            --splits 12 \
            --group ${{ matrix.group }}
        env:
          NUM_WORKERS: 0
          DP_TEST_TF2_ONLY: 1
          DP_DTYPE_PROMOTION_STRICT: 1
          DP_CI_IMPORT_PADDLE_BEFORE_TF: 1
      - name: Combine shard durations
        run: jq -s 'reduce .[] as $durations ({}; . * $durations)' .test_durations_main .test_durations_tf2 .test_durations_jax2tf .test_durations_consistent_tf2 > .test_durations_${{ matrix.group }}
      - name: Upload partial durations
        uses: actions/upload-artifact@v7
        with:
          name: split-${{ matrix.python }}-${{ matrix.group }}
          path: .test_durations_${{ matrix.group }}
          include-hidden-files: true
      - name: Upload coverage to Codecov (non-blocking)
        uses: codecov/codecov-action@v7
        continue-on-error: true
        with:
          use_oidc: true
    permissions:
      id-token: write
  update_durations:
    name: Combine and update integration test durations
    runs-on: ubuntu-slim
    strategy:
      fail-fast: false
      matrix:
        # Pull requests only run the oldest supported Python version.
        # Push and merge queue runs keep the full version matrix.
        python: ${{ fromJSON(github.event_name == 'pull_request' && '["3.10"]' || '["3.10", "3.13"]') }}
    needs: testpython
    steps:
      - name: Get durations from cache
        uses: actions/cache@v6
        with:
          path: .test_durations
          # key won't match during the first run for the given commit, but
          # restore-key will if there's a previous stored durations file,
          # so cache will both be loaded and stored
          key: test4-durations-combined-${{ matrix.python }}-${{ github.sha }}
          restore-keys: test4-durations-combined-${{ matrix.python }}
      - name: Download artifacts
        uses: actions/download-artifact@v8
        with:
          pattern: split-${{ matrix.python }}-*
          merge-multiple: true
      - name: Combine test durations
        run: jq -s 'reduce .[] as $durations ({}; . * $durations)' .test_durations_* > .test_durations
  pass:
    name: Pass testing Python
    needs: [testpython, update_durations]
    runs-on: ubuntu-slim
    if: always()
    steps:
      - name: Decide whether the needed jobs succeeded or failed
        uses: re-actors/alls-green@release/v1
        with:
          jobs: ${{ toJSON(needs) }}